中文
相关论文

相关论文: Estimation of positive definite M-matrices and str…

200 篇论文

In this paper, we study randomized and cyclic coordinate descent for convex unconstrained optimization problems. We improve the known convergence rates in some cases by using the numerical semidefinite programming performance estimation…

最优化与控制 · 数学 2022-12-26 Hadi Abbaszadehpeivasti , Etienne de Klerk , Moslem Zamani

The task of estimating a matrix given a sample of observed entries is known as the \emph{matrix completion problem}. Most works on matrix completion have focused on recovering an unknown real-valued low-rank matrix from a random sample of…

统计理论 · 数学 2014-08-27 Olga Klopp , Jean Lafond , Eric Moulines , Joseph Salmon

Let $X=C+\mathrm{E}$ with a deterministic matrix $C\in\R^{M\times M}$ and $\mathrm{E}$ some centered Gaussian $M\times M$-matrix whose entries are independent with variance $\sigma^2$. In the present work, the accuracy of reduced-rank…

概率论 · 数学 2012-05-08 Angelika Rohde

Graphical models for structured domains are powerful tools, but the computational complexities of combinatorial prediction spaces can force restrictions on models, or require approximate inference in order to be tractable. Instead of…

机器学习 · 计算机科学 2013-09-27 Stephen Bach , Bert Huang , Ben London , Lise Getoor

We consider a problem of considerable practical interest: the recovery of a data matrix from a sampling of its entries. Suppose that we observe m entries selected uniformly at random from a matrix M. Can we complete the matrix and recover…

信息论 · 计算机科学 2008-05-30 Emmanuel J. Candes , Benjamin Recht

In structured prediction problems where we have indirect supervision of the output, maximum marginal likelihood faces two computational obstacles: non-convexity of the objective and intractability of even a single gradient computation. In…

机器学习 · 统计学 2016-08-11 Aditi Raghunathan , Roy Frostig , John Duchi , Percy Liang

Methods for inference and simulation of linearly constrained Gaussian Markov Random Fields (GMRF) are computationally prohibitive when the number of constraints is large. In some cases, such as for intrinsic GMRFs, they may even be…

统计方法学 · 统计学 2021-06-04 David Bolin , Jonas Wallin

We study the problem of learning a partially observed matrix under the low rank assumption in the presence of fully observed side information that depends linearly on the true underlying matrix. This problem consists of an important…

机器学习 · 统计学 2026-02-05 Dimitris Bertsimas , Nicholas A. G. Johnson

We address the problem of minimizing a convex function over the space of large matrices with low rank. While this optimization problem is hard in general, we propose an efficient greedy algorithm and derive its formal approximation…

机器学习 · 计算机科学 2011-06-09 Shai Shalev-Shwartz , Alon Gonen , Ohad Shamir

We study an estimator with a convex formulation for recovery of low-rank matrices from rank-one projections. Using initial estimates of the factors of the target $d_1\times d_2$ matrix of rank-$r$, the estimator admits a practical…

统计理论 · 数学 2021-01-12 Sohail Bahmani , Kiryung Lee

We are concerned with an approximation problem for a symmetric positive semidefinite matrix due to motivation from a class of nonlinear machine learning methods. We discuss an approximation approach that we call {matrix ridge…

机器学习 · 统计学 2013-12-18 Zhihua Zhang

The problem of completing high-dimensional matrices from a limited set of observations arises in many big data applications, especially, recommender systems. Existing matrix completion models generally follow either a memory- or a…

机器学习 · 计算机科学 2019-09-30 Duc Minh Nguyen , Robert Calderbank , Nikos Deligiannis

This paper presents new results allowing an unknown non-Gaussian positive matrix-valued random field to be identified through a stochastic elliptic boundary value problem, solving a statistical inverse problem. A new general class of…

统计理论 · 数学 2019-02-20 Anthony Nouy , Christian Soize

Many real-world datasets can be represented in the form of a graph whose edge weights designate similarities between instances. A discrete Gaussian random field (GRF) model is a finite-dimensional Gaussian process (GP) whose prior…

机器学习 · 计算机科学 2012-09-18 Yifei Ma , Roman Garnett , Jeff Schneider

We consider the problem of predicting the covariance of a zero mean Gaussian vector, based on another feature vector. We describe a covariance predictor that has the form of a generalized linear model, i.e., an affine function of the…

机器学习 · 统计学 2021-02-01 Shane Barratt , Stephen Boyd

Optimization over low rank matrices has broad applications in machine learning. For large scale problems, an attractive heuristic is to factorize the low rank matrix to a product of two much smaller matrices. In this paper, we study the…

数值分析 · 数学 2019-03-19 Huan Li , Zhouchen Lin

Sparse Gaussian graphical models characterize sparse dependence relationships between random variables in a network. To estimate multiple related Gaussian graphical models on the same set of variables, we formulate a hierarchical model,…

统计方法学 · 统计学 2014-06-10 Yuancheng Zhu , Rina Foygel Barber

Solving symmetric positive definite linear problems is a fundamental computational task in machine learning. The exact solution, famously, is cubicly expensive in the size of the matrix. To alleviate this problem, several linear-time…

机器学习 · 计算机科学 2017-06-02 Filip de Roos , Philipp Hennig

The L1-regularized Gaussian maximum likelihood estimator (MLE) has been shown to have strong statistical guarantees in recovering a sparse inverse covariance matrix, or alternatively the underlying graph structure of a Gaussian Markov…

机器学习 · 计算机科学 2013-06-14 Cho-Jui Hsieh , Matyas A. Sustik , Inderjit S. Dhillon , Pradeep Ravikumar

The inductive matrix completion (IMC) problem is to recover a low rank matrix from few observed entries while incorporating prior knowledge about its row and column subspaces. In this work, we make three contributions to the IMC problem:…

机器学习 · 计算机科学 2022-02-01 Pini Zilber , Boaz Nadler